wrolpi/modules/zim/test/test_api.py
lrnselfreliance bfe7b8afbd
Zim estimates and searches run in a libzim worker process so a cold Zim cannot stall the API worker (#928)
* Zim search estimates run in a separate process so a cold estimate cannot stall the API worker

The global search estimates every auto-search Zim on each keystroke.  On a
large library that estimate took tens of seconds when the Zims' pages were not
cached, and every other request routed to the same Sanic worker, such as the
channel suggestions, waited behind it.  Two things held the worker: opening a
large Zim cold takes seconds (ten for a 75 GB Zim) and `Zims.get_all` did that
on the event loop; and python-libzim never releases the GIL, so the estimate
offloaded with asyncio.to_thread still froze the worker.

Everything libzim does for an estimate now runs in a standalone script started
as a subprocess (Sanic workers are daemonic, so a multiprocessing pool cannot
be forked from them).  It reads the Zim paths and search string on stdin and
writes the counts on stdout.  A Zim it cannot read is reported and left out, as
`Zims.get_all` would leave it out.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Zim searches run in the libzim worker process too

The /api/zim/search endpoints had the same stall as the estimate: they opened
every Zim through Zims.get_all and searched them with libzim, which holds the
GIL, so a thread offload still froze the Sanic worker.

The estimate script is now a general libzim worker with estimate, search and
entries jobs.  A search of all Zims sends every Zim's job to one worker
process; the API worker only headlines the returned HTML and looks up tags.
The worker also returns each Zim's metadata so Zim.__json__ does not open the
Zim again on the event loop.  Zim.entries_with_tags is split so the tagged
paths come from the database without opening the Zim.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Tagged Zim estimates count from the database, and a cancelled request kills the libzim worker

Review of the earlier commits found two gaps.  Estimates with tags selected
still went through Zims.entries_with_tags, which opened every Zim in the API
process, and after the thread offload was removed it did so on the event loop;
they now count the tagged paths in SQL and ask the worker only for metadata.
And Sanic cancels a handler at its response timeout or on disconnect, which
left the worker process running until its stdout pipe filled; the runner now
kills and reaps it on cancellation.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-11-01 13:02:26 -07:00

476 lines
21 KiB
Python

import asyncio
import json
import sys
from unittest import mock
from http import HTTPStatus
import pytest
from modules.zim import lib
from modules.zim.models import Zim
from wrolpi import flags
from wrolpi.conftest import production_like_sessions, write_lock_held_briefly
from wrolpi.downloader import Download
@pytest.mark.asyncio
async def test_zim_search(async_client, test_session, test_zim, tag_factory, assert_zim_search):
"""Entries can be tagged and retrieved using their containing Zim."""
tag1, tag2 = await tag_factory(), await tag_factory()
test_zim.tag_entry(test_session, tag1.name, 'one')
test_zim.tag_entry(test_session, tag2.name, 'one')
test_zim.tag_entry(test_session, tag1.name, 'two')
test_session.commit()
# Test searching with only `search_str`. (Ranks/headlines come from FTS5 `headline_texts`.)
await assert_zim_search('one', 1, {
'path': test_zim.path,
'search': [
# Entry "One" contains a 'one' in the title, and the text.
{'path': 'one', 'headline': 'This is the first item', 'rank': 1e-06},
# Home only contains one 'one'.
{'path': 'home', 'rank': 8.8e-07, 'headline': '…an example ZIM file for testing.\n<b>One</b>\nTwo', },
],
'estimate': 2,
})
await assert_zim_search('two', 1, {
'path': test_zim.path,
'search': [{'path': 'two', 'headline': 'This is the second item', 'rank': 1e-06},
{'path': 'home', 'headline': '…One\n<b>Two</b>', 'rank': 8.8e-07}],
'estimate': 2,
})
await assert_zim_search('item', 1, {
'path': test_zim.path,
'search': [{'path': 'one', 'headline': 'This is the first <b>item</b>', 'rank': 1e-06},
{'path': 'two', 'headline': 'This is the second <b>item</b>', 'rank': 1e-06}],
'estimate': 2,
})
# Test searching with `search_str` and `tag_names`.
await assert_zim_search('one', 1, tag_names=[tag2.name, ], expected={
'search': [
# Only entry "One" is tagged with Tag 2.
{'path': 'one', 'headline': 'This is the first item', 'rank': 1e-06},
],
'estimate': 1,
})
await assert_zim_search('one', 1, tag_names=[tag1.name, tag2.name], expected={
'search': [
# Only "One" is tagged with Tag 1 and contains "one".
{'path': 'one', 'headline': 'This is the first item', 'rank': 1e-06},
],
'estimate': 1,
})
await assert_zim_search('two', 1, tag_names=[tag1.name, ], expected={
'search': [
# Only "Two" was tagged with Tag 1 and contains "two".
{'path': 'two', 'headline': 'This is the second item', 'rank': 1e-06},
],
'estimate': 1,
})
await assert_zim_search('two', 1, tag_names=[tag2.name, ], expected={
# Two was not tagged with Tag 1.
'search': [],
'estimate': 0,
})
# Test search with only `tag_names`.
await assert_zim_search('', 1, tag_names=[tag1.name, tag2.name], expected={
'search': [
# Return all entries that are tagged with the Tags.
{'path': 'one', 'headline': 'This is the first item', 'rank': 0.0, 'tag_names': ['one', 'two']},
],
'estimate': 1,
})
@pytest.mark.asyncio
async def test_entries_by_tag(async_client, test_session, test_zim, tag_factory):
"""Entries can be tagged and retrieved using their containing Zim."""
tag1, tag2 = await tag_factory(), await tag_factory()
test_zim.tag_entry(test_session, tag1.name, 'one')
test_zim.tag_entry(test_session, tag2.name, 'one')
test_zim.tag_entry(test_session, tag1.name, 'two')
test_session.commit()
result = test_zim.entries_with_tags(test_session, [tag1.name, tag2.name])
assert [(i.path, i.title) for i in result] == [('one', 'One'), ]
result = test_zim.entries_with_tags(test_session, [tag1.name, ])
assert [(i.path, i.title) for i in result] == [('one', 'One'), ('two', 'Two')]
result = test_zim.entries_with_tags(test_session, [tag2.name, ])
assert [(i.path, i.title) for i in result] == [('one', 'One'), ]
@pytest.mark.asyncio
async def test_zim_crud(async_client, test_session, test_directory, test_zim):
request, response = await async_client.get('/api/zim')
assert response.status_code == HTTPStatus.OK
assert len(response.json['zims']) == 1
assert response.json['zims'][0]['path'] == test_zim.path.name
request, response = await async_client.delete('/api/zim/1')
assert response.status_code == HTTPStatus.NO_CONTENT
assert not test_zim.path.exists()
assert test_session.query(Zim).count() == 0
@pytest.mark.asyncio
async def test_zim_tag_and_untag(async_client, test_session, test_zim, tag_factory):
"""Zim entries can be Tagged and Untagged."""
tag1, tag2 = await tag_factory(), await tag_factory()
test_session.commit()
# Entries can be tagged in the API.
content = dict(tag_name=tag1.name, zim_id=test_zim.id, zim_entry='home')
request, response = await async_client.post('/api/zim/tag', content=json.dumps(content))
assert response.status_code == HTTPStatus.CREATED
# Entries can be untagged in the API.
content = dict(tag_name=tag1.name, zim_id=test_zim.id, zim_entry='home')
request, response = await async_client.post('/api/zim/untag', content=json.dumps(content))
assert response.status_code == HTTPStatus.NO_CONTENT
# Cannot untag twice.
content = dict(tag_name=tag1.name, zim_id=test_zim.id, zim_entry='home')
request, response = await async_client.post('/api/zim/untag', content=json.dumps(content))
assert response.status_code == HTTPStatus.NOT_FOUND
@pytest.mark.asyncio
async def test_zim_subscribe(test_session, async_client):
"""A Kiwix subscription can be scheduled in the API. The language can be changed."""
# Subscribe to English.
content = dict(name='Wikipedia (mini)', language='en')
request, response = await async_client.post('/api/zim/subscribe', content=json.dumps(content))
assert response.status_code == HTTPStatus.CREATED
download: Download = test_session.query(Download).one()
assert download.url == 'https://download.kiwix.org/zim/wikipedia/wikipedia_en_all_mini_'
assert download.info_json == {'language': 'en', 'name': 'Wikipedia (mini)'}
assert download.frequency
request, response = await async_client.get('/api/zim/subscribe')
assert response.status_code == HTTPStatus.OK
assert response.json['subscriptions'] == {
'Wikipedia (mini)': {'download_id': 1,
'download_url': 'https://download.kiwix.org/zim/wikipedia/wikipedia_en_all_mini_',
'id': 1,
'language': 'en',
'name': 'Wikipedia (mini)'}}
# Change subscription to French.
content = dict(name='Wikipedia (mini)', language='fr')
request, response = await async_client.post('/api/zim/subscribe', content=json.dumps(content))
assert response.status_code == HTTPStatus.CREATED
assert test_session.query(Download).count() == 1
download: Download = test_session.query(Download).one()
assert download.url == 'https://download.kiwix.org/zim/wikipedia/wikipedia_fr_all_mini_'
assert download.info_json == {'language': 'fr', 'name': 'Wikipedia (mini)'}
assert download.frequency
request, response = await async_client.get('/api/zim/subscribe')
assert response.status_code == HTTPStatus.OK
assert response.json['subscriptions'] == {
'Wikipedia (mini)': {'download_id': 1,
'download_url': 'https://download.kiwix.org/zim/wikipedia/wikipedia_fr_all_mini_',
'id': 1,
'language': 'fr',
'name': 'Wikipedia (mini)'}}
# Delete subscription.
request, response = await async_client.delete('/api/zim/subscribe/1')
assert response.status_code == HTTPStatus.NO_CONTENT
request, response = await async_client.get('/api/zim/subscribe')
assert response.status_code == HTTPStatus.OK
assert response.json['subscriptions'] == {}
# No subscriptions or downloads.
assert test_session.query(lib.ZimSubscription).count() == 0
assert test_session.query(Download).count() == 0
# English Stack Exchange is special.
content = dict(name='Stackoverflow (Stack Exchange)', language='en')
request, response = await async_client.post('/api/zim/subscribe', content=json.dumps(content))
assert response.status_code == HTTPStatus.CREATED
download: Download = test_session.query(Download).one()
assert download.url == 'https://download.kiwix.org/zim/stack_exchange/stackoverflow.com_en_all_'
@pytest.mark.asyncio
async def test_get_zim_entry(test_session, async_client, test_zim):
request, response = await async_client.get('/api/zim/1/entry/home')
assert response.status_code == HTTPStatus.OK
request, response = await async_client.get('/api/zim/1/entry/does not exist')
assert response.status_code == HTTPStatus.NOT_FOUND
def test_parse_name():
"""Zim file names that match the kiwix naming scheme are parsed. Non-matching names raise ValueError."""
import pathlib
from datetime import datetime
name, date = lib.parse_name(pathlib.Path('wikipedia_en_all_maxi_2023-01.zim'))
assert name == 'wikipedia_en_all_maxi'
assert date == datetime(2023, 1, 1)
with pytest.raises(ValueError):
lib.parse_name(pathlib.Path('edibleplantdb.zim'))
with pytest.raises(ValueError):
lib.parse_name(pathlib.Path('nodate.zim'))
@pytest.mark.asyncio
async def test_find_outdated_zim_files(test_session, test_directory, test_zim_bytes, async_client):
"""Outdated Zim files are found and reported. They can automatically be deleted."""
# Can search empty directory.
outdated, current = lib.find_outdated_zim_files()
assert not outdated and not current
(test_directory / 'zims/books').mkdir(parents=True)
wikibooks_one = test_directory / 'zims/books/wikibooks_en_nopic_maxi_2023-01.zim' # unique
wikipedia_one = test_directory / 'zims/wikipedia_en_all_maxi_2023-01.zim' # outdated
wikipedia_two = test_directory / 'zims/wikipedia_en_all_maxi_2023-02.zim' # keep this one
asdf = test_directory / 'zims/asdf.zim' # Name cannot be parsed.
wikibooks_one.write_bytes(test_zim_bytes)
wikipedia_one.write_bytes(test_zim_bytes)
wikipedia_two.write_bytes(test_zim_bytes)
asdf.write_bytes(test_zim_bytes)
empty = test_directory / 'zims/wikipedia_en_all_maxi_2023-03.zim' # empty files should be ignored.
empty.touch()
request, response = await async_client.get('/api/zim/outdated')
assert response.status_code == HTTPStatus.OK
assert response.json['outdated'] == [str(wikipedia_one.relative_to(test_directory)), ]
request, response = await async_client.delete('/api/zim/outdated')
assert response.status_code == HTTPStatus.NO_CONTENT
# Only the outdated was deleted.
assert wikibooks_one.is_file()
assert not wikipedia_one.exists()
assert wikipedia_two.is_file()
assert asdf.is_file()
assert empty.is_file()
@pytest.mark.asyncio
async def test_delete_outdated_zims_clears_stale_flag(test_session, test_directory, test_zim_bytes, async_client,
flags_lock):
"""Deleting outdated Zims always leaves the `outdated_zims` flag matching disk, even when nothing was deleted."""
(test_directory / 'zims').mkdir(parents=True)
(test_directory / 'zims/wikipedia_en_all_maxi_2023-02.zim').write_bytes(test_zim_bytes)
flags.outdated_zims.set()
request, response = await async_client.get('/api/zim/outdated')
assert response.status_code == HTTPStatus.OK
assert response.json['outdated'] == []
request, response = await async_client.delete('/api/zim/outdated')
assert response.status_code == HTTPStatus.NO_CONTENT
assert not flags.outdated_zims.is_set(), 'Flag should be recomputed even when nothing was deleted'
@pytest.mark.asyncio
async def test_search_estimates(test_session, async_client, zim_factory):
zim_factory('test zim')
test_session.commit()
body = dict(search_str='one')
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert response.status_code == HTTPStatus.OK
assert len(response.json['zims_estimates']) == 1
assert response.json['zims_estimates'][0]['estimate'] == 2
@pytest.mark.asyncio
async def test_zim_auto_search(test_session, async_client, zim_factory):
"""The auto-searching of any Zim file can be toggled."""
zim = zim_factory('test_zim_auto_search.zim')
assert zim.auto_search is True, 'Zim should be searched by default.'
# Zim is estimated by default.
body = dict(search_str='one')
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert response.status_code == HTTPStatus.OK
assert len(response.json['zims_estimates']) == 1
# Change auto_search so Zim is not estimated by default.
body = dict(auto_search=False)
request, response = await async_client.post(f'/api/zim/{zim.id}/auto_search', json=body)
assert response.status_code == HTTPStatus.NO_CONTENT
assert zim.auto_search is False
# Estimates are empty because the only Zim was filtered out.
body = dict(search_str='one')
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert response.status_code == HTTPStatus.OK
assert len(response.json['zims_estimates']) == 0
# Change auto_search so Zim is now estimated again.
body = dict(auto_search=True)
request, response = await async_client.post(f'/api/zim/{zim.id}/auto_search', json=body)
assert response.status_code == HTTPStatus.NO_CONTENT
assert zim.auto_search is True
# Zim is estimated by default.
body = dict(search_str='one')
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert response.status_code == HTTPStatus.OK
assert len(response.json['zims_estimates']) == 1
@pytest.mark.asyncio
@pytest.mark.parametrize('step', ['auto_search', 'tag', 'untag', 'subscribe', 'unsubscribe'])
async def test_zim_writes_wait_for_a_concurrent_writer(async_client, test_session, test_zim, tag_factory, step):
"""These requests read before they write, so each must begin as a writer: SQLite fails a deferred
transaction's lock upgrade instantly ("database is locked") if another connection wrote meanwhile."""
tag = await tag_factory()
test_session.commit()
entry = dict(tag_name=tag.name, zim_id=test_zim.id, zim_entry='home')
if step == 'untag':
await lib.add_tag(test_session, tag.name, test_zim.id, 'home')
if step == 'unsubscribe':
await lib.subscribe(test_session, 'Wikipedia (mini)', 'en')
test_session.commit()
db_file = test_session.get_bind().url.database
with production_like_sessions(test_session):
# Held past any slow work a request does before it writes.
with write_lock_held_briefly(db_file, seconds=3):
if step == 'auto_search':
_, response = await async_client.post(f'/api/zim/{test_zim.id}/auto_search',
content=json.dumps(dict(auto_search=False)))
elif step in ('tag', 'untag'):
_, response = await async_client.post(f'/api/zim/{step}', content=json.dumps(entry))
elif step == 'subscribe':
_, response = await async_client.post(
'/api/zim/subscribe', content=json.dumps(dict(name='Wikipedia (mini)', language='en')))
else:
_, response = await async_client.delete('/api/zim/subscribe/1')
assert response.status_code in (HTTPStatus.CREATED, HTTPStatus.NO_CONTENT), response.body
@pytest.mark.asyncio
async def test_delete_zim_waits_for_a_concurrent_writer(async_client, test_session, test_zim):
"""Deleting a Zim must delete its row as well as its file, even while something else is writing. It wrote
in the request's deferred transaction, so its commit in the response middleware failed ("database is
locked") after the file was deleted and the response was sent."""
zim_id, zim_path = test_zim.id, test_zim.path
test_session.commit()
db_file = test_session.get_bind().url.database
with production_like_sessions(test_session) as maker:
with write_lock_held_briefly(db_file, seconds=3):
_, response = await async_client.delete(f'/api/zim/{zim_id}')
assert response.status_code == HTTPStatus.NO_CONTENT, response.body
assert not zim_path.exists()
with maker() as session:
assert session.query(Zim).filter_by(id=zim_id).one_or_none() is None
@pytest.mark.asyncio
async def test_estimate_zims_runs_outside_the_api_process(test_session, zim_factory):
"""libzim holds the GIL, so estimates run in a separate process rather than a thread of the API worker."""
zim = zim_factory('test zim')
test_session.commit()
with mock.patch('modules.zim.lib.asyncio.create_subprocess_exec', wraps=asyncio.create_subprocess_exec) as m:
counts = await lib.estimate_zims(test_session, 'one')
assert counts == {zim: 2}
assert m.call_args.args[:2] == (sys.executable, '-I')
@pytest.mark.asyncio
async def test_estimate_zims_skips_a_zim_it_cannot_read(test_session, zim_factory):
"""A Zim the estimate process cannot open is left out of the estimates, like `Zims.get_all` leaves it out."""
good = zim_factory('good zim')
bad = zim_factory('bad zim')
test_session.commit()
bad.path.write_bytes(b'not a zim file')
counts = await lib.estimate_zims(test_session, 'one')
assert counts == {good: 2}
bad.path.unlink()
counts = await lib.estimate_zims(test_session, 'one')
assert counts == {good: 2}
@pytest.mark.asyncio
async def test_zim_search_runs_outside_the_api_process(async_client, test_session, test_zim):
"""Zim searches, like estimates, do all their libzim work in the worker script's process."""
with mock.patch('modules.zim.lib.asyncio.create_subprocess_exec', wraps=asyncio.create_subprocess_exec) as m:
request, response = await async_client.post(f'/api/zim/search/{test_zim.id}', json=dict(search_str='one'))
assert response.status_code == HTTPStatus.OK
assert [i['path'] for i in response.json['zim']['search']] == ['one', 'home']
assert response.json['zim']['metadata']['title'], 'Metadata should come from the worker'
request, response = await async_client.post('/api/zim/search', json=dict(search_str='one'))
assert response.status_code == HTTPStatus.OK
assert [i['path'] for i in response.json['zims'][0]['search']] == ['one', 'home']
assert m.call_count == 2
assert all(call.args[:2] == (sys.executable, '-I') for call in m.call_args_list)
@pytest.mark.asyncio
async def test_search_all_zims_skips_a_zim_it_cannot_read(async_client, test_session, zim_factory):
"""One unreadable Zim does not fail the search of all Zims."""
good = zim_factory('good zim')
bad = zim_factory('bad zim')
test_session.commit()
bad.path.write_bytes(b'not a zim file')
request, response = await async_client.post('/api/zim/search', json=dict(search_str='one'))
assert response.status_code == HTTPStatus.OK
zims = response.json['zims']
assert len(zims) == 1 and zims[0]['path'].endswith('good zim')
assert zims[0]['estimate'] == 2
@pytest.mark.asyncio
async def test_tagged_search_estimates_do_not_open_zims(async_client, test_session, test_zim, tag_factory):
"""Estimates with tags count from the database; the API process never opens a Zim, even for its metadata."""
tag1, tag2 = await tag_factory(), await tag_factory()
test_zim.tag_entry(test_session, tag1.name, 'one')
test_zim.tag_entry(test_session, tag1.name, 'two')
test_zim.tag_entry(test_session, tag2.name, 'one')
test_session.commit()
with mock.patch('modules.zim.models.Zim.get_zim', side_effect=AssertionError('opened a Zim in the API')):
body = dict(search_str='one', tag_names=[tag1.name])
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert response.status_code == HTTPStatus.OK
assert [(i['estimate'], bool(i['metadata']['title'])) for i in response.json['zims_estimates']] \
== [(2, True)]
body = dict(search_str='', tag_names=[tag1.name, tag2.name])
request, response = await async_client.post('/api/zim/search_estimates', json=body)
assert [i['estimate'] for i in response.json['zims_estimates']] == [1]
@pytest.mark.asyncio
async def test_cancelled_libzim_jobs_kill_the_worker(test_directory):
"""Sanic cancels a handler at its response timeout or on disconnect; the worker process must not outlive it."""
slow_worker = test_directory / 'slow_worker.py'
slow_worker.write_text('import time; time.sleep(60)')
procs = []
create_subprocess_exec = asyncio.create_subprocess_exec
async def spy(*args, **kwargs):
proc = await create_subprocess_exec(*args, **kwargs)
procs.append(proc)
return proc
with mock.patch('modules.zim.lib.LIBZIM_WORKER', slow_worker), \
mock.patch('modules.zim.lib.asyncio.create_subprocess_exec', side_effect=spy):
task = asyncio.create_task(lib.run_libzim_jobs([]))
while not procs:
await asyncio.sleep(0.01)
task.cancel()
with pytest.raises(asyncio.CancelledError):
await task
assert procs[0].returncode is not None, 'The worker was killed and reaped'